Warning! The directory is not yet complete and will be amended until the beginning of the term.
390043 UK VGSCO Statistical Inference via Convex Optimization (2018S)
Continuous assessment of course work
Labels
Registration/Deregistration
Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).
- Registration is open from Mo 05.03.2018 12:00 to Th 31.05.2018 23:59
- Deregistration possible until Th 31.05.2018 23:59
Details
max. 25 participants
Language: English
Lecturers
Classes
Block, May 23 – June 4, 2018
Seminar Room 3.307 (3rd floor, Faculty of Business, Economics and Statistics)
Thursday, 24.05. 10:00 - 12:30
Friday, 25.05. 10:00 - 12:30Tuesday, 29.05. 15:00 - 17:30
Wednesday, 30.05. 10:00 - 12:30
Friday, 01.06. 10:00 - 12:30
Monday, 04.06. 10:00 - 12:30
Information
Aims, contents and method of the course
Assessment and permitted materials
To be graded, a participant should submit at the end of the classes solutions to two Exercises from Lecture Notes available at https://www2.isye.gatech.edu/~nemirovs/StatOpt_LN.pdf (selection of Exercises to be solved is up to participant). Preparing solutions is a take-home task with no restrictions on material used.
The grade will be based on the quality of the solution as assessed by the lecturer.
The grade will be based on the quality of the solution as assessed by the lecturer.
Minimum requirements and assessment criteria
Examination topics
Course contents as reflected in Exercises from Lecture Notes.
Reading list
a) Lecture Notes: Anatoli Juditsky, Arkadi Nemirovski "Statistical Inferences via Convex Optimization''
https://www2.isye.gatech.edu/~nemirovs/StatOpt_LN.pdfb) Transparencies
https://www2.isye.gatech.edu/~nemirovs/SCOTransp.pdf
https://www2.isye.gatech.edu/~nemirovs/StatOpt_LN.pdfb) Transparencies
https://www2.isye.gatech.edu/~nemirovs/SCOTransp.pdf
Association in the course directory
Last modified: Fr 31.08.2018 08:43
What is in the scope of the course, are inference routines motivated and justified by Optimization Theory (Convex Analysis, Conic Programming, Saddle Points, Duality...), the working horse being convex optimization.
This choice is motivated by
- nice geometry of convex sets, functions, and optimization problems
- computational tractability of convex optimization implying computational efficiency of statistical inferences stemming from Convex Optimization.For more comments on "course's philosophy'' and for detailed description of course's contents, see Preface and Table of Contents in Lecture Notes available at
https://www2.isye.gatech.edu/~nemirovs/StatOpt_LN.pdf